An open-source system for building-height estimation using street-view images, deep learning, and building footprints / by Ala'a Al-Habashna.: CS18-001/2020-2E-PDF

"Deploying street‑view imagery for information extraction has been increasingly considered recently by both industry and academia. Various efforts have been paid to extract information, relevant to various applications, from street‑view images. This includes sidewalk detection in cities to help city planners and building instance classification. Building height is an important piece of information that can be extracted from street‑view imagery. Such key information has various important applications such as economic analysis as well as developing 3D maps of cities. In this project, an open‑source system is developed for automatic estimation of building height from street‑view images using Deep Learning (DL), advanced image processing techniques, and geospatial data. Both street‑view images and the needed geospatial data are becoming pervasive and available through multiple platforms. The goal of the developed system is to ultimately be used to enrich the Open Database of Buildings (ODB), that has been published by Statistics Canada, as a part of the Linkable Open Data Environment (LODE). In this paper, the developed system is explained. Furthermore, some of the obtained results for building‑height estimation are presented. Some challenging cases and the scalability of the system are discussed as well"--Summary, page 7.

Permanent link to this Catalogue record:
publications.gc.ca/pub?id=9.894178&sl=0

• MARC XML format
• MARC HTML format

Request alternate formats